Copertina

Task-conditioned adaptation of visual features in multi-task policy learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Marza, Pierre, Matignon, Laetitia, Simonin, Olivier, Wolf, Christian
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Machine Learning Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Reasoning in visual navigation of end-to-end trained agents: a dynamical systems approach
di: Janny, Steeven, et al.
Pubblicazione: (2025)

Towards agricultural autonomy: crop row detection under varying field conditions using deep learning
di: de Silva, Rajitha, et al.
Pubblicazione: (2021)

On the importance of cross-task features for class-incremental learning
di: Soutif--Cormerais, Albin, et al.
Pubblicazione: (2021)

Domain Adaptation Through Task Distillation
di: Zhou, Brady, et al.
Pubblicazione: (2020)

M2H: Multi-Task Learning with Efficient Window-Based Cross-Task Attention for Monocular Spatial Perception
di: Udugama, U. V. B. L, et al.
Pubblicazione: (2025)

Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge
di: Larchenko, Ilia, et al.
Pubblicazione: (2025)

Generalizable Dense Reward for Long-Horizon Robotic Tasks
di: Yong, Silong, et al.
Pubblicazione: (2026)

Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
di: Guruprasad, Pranav, et al.
Pubblicazione: (2024)

AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation
di: Tan, Hengkai, et al.
Pubblicazione: (2025)

Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks
di: Eisner, Ben, et al.
Pubblicazione: (2024)

Transferable Tactile Transformers for Representation Learning Across Diverse Sensors and Tasks
di: Zhao, Jialiang, et al.
Pubblicazione: (2024)

A Survey on Deep Multi-Task Learning in Connected Autonomous Vehicles
di: Wang, Jiayuan, et al.
Pubblicazione: (2025)

Next-Future: Sample-Efficient Policy Learning for Robotic-Arm Tasks
di: Özgür, Fikrican, et al.
Pubblicazione: (2025)

Reinforcement Learning from Wild Animal Videos
di: Chane-Sane, Elliot, et al.
Pubblicazione: (2024)

Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions
di: Kim, Kyungmin, et al.
Pubblicazione: (2024)

GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields
di: Ze, Yanjie, et al.
Pubblicazione: (2023)

Terrain characterisation for online adaptability of automated sonar processing: Lessons learnt from operationally applying ATR to sidescan sonar in MCM applications
di: Guerneve, Thomas, et al.
Pubblicazione: (2024)

Augmented Reality based Simulated Data (ARSim) with multi-view consistency for AV perception networks
di: Anwar, Aqeel, et al.
Pubblicazione: (2024)

Under pressure: learning-based analog gauge reading in the wild
di: Reitsma, Maurits, et al.
Pubblicazione: (2024)

VertiFormer: A Data-Efficient Multi-Task Transformer for Off-Road Robot Mobility
di: Nazeri, Mohammad, et al.
Pubblicazione: (2025)

Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation
di: Kuang, Yuxuan, et al.
Pubblicazione: (2026)

SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution
di: Liang, Zhixuan, et al.
Pubblicazione: (2023)

SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Dataset
di: Mehr, Goodarz, et al.
Pubblicazione: (2025)

DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving Scenes
di: Hou, Qirui, et al.
Pubblicazione: (2025)

Detecting spills using thermal imaging, pretrained deep learning models, and a robotic platform
di: Yeghiyan, Gregory, et al.
Pubblicazione: (2025)

Real-time object detection and robotic manipulation for agriculture using a YOLO-based learning approach
di: Zhao, Hongyu, et al.
Pubblicazione: (2024)

SaliencyI2PLoc: saliency-guided image-point cloud localization using contrastive learning
di: Li, Yuhao, et al.
Pubblicazione: (2024)

UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene
di: Maurer, Christian, et al.
Pubblicazione: (2025)

Experimental investigation of pose informed reinforcement learning for skid-steered visual navigation
di: Salvi, Ameya, et al.
Pubblicazione: (2025)

Unsupervised Point Cloud Registration with Self-Distillation
di: Löwens, Christian, et al.
Pubblicazione: (2024)

PseudoMapTrainer: Learning Online Mapping without HD Maps
di: Löwens, Christian, et al.
Pubblicazione: (2025)

A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset
di: Woerner, Stefano, et al.
Pubblicazione: (2024)

GenSim: Generating Robotic Simulation Tasks via Large Language Models
di: Wang, Lirui, et al.
Pubblicazione: (2023)

Bimanual Dexterity for Complex Tasks
di: Shaw, Kenneth, et al.
Pubblicazione: (2024)

Learning Vision-Based Omnidirectional Navigation: A Teacher-Student Approach Using Monocular Depth Estimation
di: Finke, Jan, et al.
Pubblicazione: (2026)

Towards Task-Oriented Flying: Framework, Infrastructure, and Principles
di: Huang, Kangyao, et al.
Pubblicazione: (2025)

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation
di: Ma, Xiao, et al.
Pubblicazione: (2024)

PerAct2: Benchmarking and Learning for Robotic Bimanual Manipulation Tasks
di: Grotz, Markus, et al.
Pubblicazione: (2024)

CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers
di: Mallis, Dimitrios, et al.
Pubblicazione: (2024)

TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation
di: Pan, Chuer, et al.
Pubblicazione: (2022)